{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:VSMFVE5HK4JHPC5DKHXS5COP2A","short_pith_number":"pith:VSMFVE5H","canonical_record":{"source":{"id":"2207.06216","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-07-13T14:21:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b24575cd4710f77c88acf84dcaeff18649c1549fcaf4c401ffd05541ac7ed320","abstract_canon_sha256":"d830f204b6489802bb36f5a4b2e3d2cca3052d86cb0b1b75ebf8ed8018f0500f"},"schema_version":"1.0"},"canonical_sha256":"ac985a93a75712778ba351ef2e89cfd0249f67f53d0f78a130a842903e0142f7","source":{"kind":"arxiv","id":"2207.06216","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.06216","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"arxiv_version","alias_value":"2207.06216v1","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.06216","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"pith_short_12","alias_value":"VSMFVE5HK4JH","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"pith_short_16","alias_value":"VSMFVE5HK4JHPC5D","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"pith_short_8","alias_value":"VSMFVE5H","created_at":"2026-07-05T04:40:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:VSMFVE5HK4JHPC5DKHXS5COP2A","target":"record","payload":{"canonical_record":{"source":{"id":"2207.06216","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-07-13T14:21:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b24575cd4710f77c88acf84dcaeff18649c1549fcaf4c401ffd05541ac7ed320","abstract_canon_sha256":"d830f204b6489802bb36f5a4b2e3d2cca3052d86cb0b1b75ebf8ed8018f0500f"},"schema_version":"1.0"},"canonical_sha256":"ac985a93a75712778ba351ef2e89cfd0249f67f53d0f78a130a842903e0142f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:02.780842Z","signature_b64":"G4Iw1JzSJuQT1NTu9E+qy8fHc7kIPej0/pIBbz1h6qVef2017+O26tYeimyn/AHOKMaCUl9IAi3zUqV8XQOjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac985a93a75712778ba351ef2e89cfd0249f67f53d0f78a130a842903e0142f7","last_reissued_at":"2026-07-05T04:40:02.780463Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:02.780463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.06216","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:40:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hvXDz+2yewnL9VtNNybOBXILb/GJA9qdjb9PSPrvCNZLapgvZlsJK6gKrXlt9voq9jYQZagNAtHaw/zR/8+6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:46:15.150838Z"},"content_sha256":"9acb8ce6502a0cb25f2c01c769e3bd7487cdad72d1e7d8b31d73f1729a3c665d","schema_version":"1.0","event_id":"sha256:9acb8ce6502a0cb25f2c01c769e3bd7487cdad72d1e7d8b31d73f1729a3c665d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:VSMFVE5HK4JHPC5DKHXS5COP2A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Goal-Oriented Sensitivity Analysis of Hyperparameters in Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"David Lugato, Ga\\\"el Po\\\"ette, Paul Novello, Pietro Marco Congedo","submitted_at":"2022-07-13T14:21:12Z","abstract_excerpt":"Tackling new machine learning problems with neural networks always means optimizing numerous hyperparameters that define their structure and strongly impact their performances. In this work, we study the use of goal-oriented sensitivity analysis, based on the Hilbert-Schmidt Independence Criterion (HSIC), for hyperparameter analysis and optimization. Hyperparameters live in spaces that are often complex and awkward. They can be of different natures (categorical, discrete, boolean, continuous), interact, and have inter-dependencies. All this makes it non-trivial to perform classical sensitivity"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06216","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2207.06216/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:40:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7szPQ/DuAaaPxbuULYQayHXoUpsULRJPek76hExlonhrqsUkBx6ov8XOVL0Hz6quZ1Ar7smqkc/R9zw+5Z1PCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:46:15.151356Z"},"content_sha256":"7c85d3ddbfd608b5adaba7a777efe80378efc17e2fd538464e0d2624eaf92966","schema_version":"1.0","event_id":"sha256:7c85d3ddbfd608b5adaba7a777efe80378efc17e2fd538464e0d2624eaf92966"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VSMFVE5HK4JHPC5DKHXS5COP2A/bundle.json","state_url":"https://pith.science/pith/VSMFVE5HK4JHPC5DKHXS5COP2A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VSMFVE5HK4JHPC5DKHXS5COP2A/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T17:46:15Z","links":{"resolver":"https://pith.science/pith/VSMFVE5HK4JHPC5DKHXS5COP2A","bundle":"https://pith.science/pith/VSMFVE5HK4JHPC5DKHXS5COP2A/bundle.json","state":"https://pith.science/pith/VSMFVE5HK4JHPC5DKHXS5COP2A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VSMFVE5HK4JHPC5DKHXS5COP2A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VSMFVE5HK4JHPC5DKHXS5COP2A","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d830f204b6489802bb36f5a4b2e3d2cca3052d86cb0b1b75ebf8ed8018f0500f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-07-13T14:21:12Z","title_canon_sha256":"b24575cd4710f77c88acf84dcaeff18649c1549fcaf4c401ffd05541ac7ed320"},"schema_version":"1.0","source":{"id":"2207.06216","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.06216","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"arxiv_version","alias_value":"2207.06216v1","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.06216","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"pith_short_12","alias_value":"VSMFVE5HK4JH","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"pith_short_16","alias_value":"VSMFVE5HK4JHPC5D","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"pith_short_8","alias_value":"VSMFVE5H","created_at":"2026-07-05T04:40:02Z"}],"graph_snapshots":[{"event_id":"sha256:7c85d3ddbfd608b5adaba7a777efe80378efc17e2fd538464e0d2624eaf92966","target":"graph","created_at":"2026-07-05T04:40:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2207.06216/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tackling new machine learning problems with neural networks always means optimizing numerous hyperparameters that define their structure and strongly impact their performances. In this work, we study the use of goal-oriented sensitivity analysis, based on the Hilbert-Schmidt Independence Criterion (HSIC), for hyperparameter analysis and optimization. Hyperparameters live in spaces that are often complex and awkward. They can be of different natures (categorical, discrete, boolean, continuous), interact, and have inter-dependencies. All this makes it non-trivial to perform classical sensitivity","authors_text":"David Lugato, Ga\\\"el Po\\\"ette, Paul Novello, Pietro Marco Congedo","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-07-13T14:21:12Z","title":"Goal-Oriented Sensitivity Analysis of Hyperparameters in Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06216","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9acb8ce6502a0cb25f2c01c769e3bd7487cdad72d1e7d8b31d73f1729a3c665d","target":"record","created_at":"2026-07-05T04:40:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d830f204b6489802bb36f5a4b2e3d2cca3052d86cb0b1b75ebf8ed8018f0500f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-07-13T14:21:12Z","title_canon_sha256":"b24575cd4710f77c88acf84dcaeff18649c1549fcaf4c401ffd05541ac7ed320"},"schema_version":"1.0","source":{"id":"2207.06216","kind":"arxiv","version":1}},"canonical_sha256":"ac985a93a75712778ba351ef2e89cfd0249f67f53d0f78a130a842903e0142f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac985a93a75712778ba351ef2e89cfd0249f67f53d0f78a130a842903e0142f7","first_computed_at":"2026-07-05T04:40:02.780463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:40:02.780463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G4Iw1JzSJuQT1NTu9E+qy8fHc7kIPej0/pIBbz1h6qVef2017+O26tYeimyn/AHOKMaCUl9IAi3zUqV8XQOjDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:40:02.780842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.06216","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9acb8ce6502a0cb25f2c01c769e3bd7487cdad72d1e7d8b31d73f1729a3c665d","sha256:7c85d3ddbfd608b5adaba7a777efe80378efc17e2fd538464e0d2624eaf92966"],"state_sha256":"ae2afa50fd7fb0fdd5634f6c8f194a43b869dfe3e4e9082c11174c320c3be08c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rWi8S8nQ3SKBgodnVuu7s2HbqEJNK8xcBrGRGUiKP1DdhBnpst8fbG1Ogabt4o5ekLsZHjeXStbnqgl2BkkLDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:46:15.156695Z","bundle_sha256":"cf0bb1b492034a32cb98008cfeed19fa0fe3f4df6d49679519283fde106dd475"}}